The Neural Autoregressive Distribution Estimator

Hugo Larochelle, Iain Murray

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract / Description of output

We describe a new approach for modeling the distribution of high-dimensional vectors of discrete variables. This model is inspired by the restricted Boltzmann machine (RBM), which has been shown to be a powerful model of such distributions. However, an RBM typically does not provide a tractable distribution estimator, since evaluating the probability it assigns to some given observation requires the computation of the so-called partition function, which itself is intractable for RBMs of even moderate size. Our model circumvents this difficulty by decomposing the joint distribution of observations into tractable conditional distributions and modeling each conditional using a non-linear function similar to a conditional of an RBM. Our model can also be interpreted as an autoencoder wired such that its output can be used to assign valid probabilities to observations. We show that this new model outperforms other multivariate binary distribution estimators on several datasets and performs similarly to a large (but intractable) RBM.
Original languageEnglish
Title of host publicationProceedings of the 14th International Conference on Artificial Intelligence and Statistics (AISTATS)
Number of pages9
Publication statusPublished - 2011

Publication series

Name JMLR: Workshop and Conference Proceedings
ISSN (Electronic)1533-7928


Dive into the research topics of 'The Neural Autoregressive Distribution Estimator'. Together they form a unique fingerprint.

Cite this